Agent-Shield
Server Details
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- Repository
- startekenterprises-ai/agent-shield
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 1 tool
With only one tool, there is no possibility of selecting the wrong tool or confusing overlapping purposes. The single tool has a clearly defined operation.
The name 'shield.scan' is readable and follows a clear namespace.verb convention. With only one tool there is no multi-tool pattern to violate, though it is not the more typical verb_noun style.
A single scan tool is focused but thin for a server called Agent-Shield. Related operations such as URL scanning, redaction, or policy configuration could reasonably exist, but the current surface is not overwhelming.
The tool covers the core scanning use case across prompt injection, secrets, PII, and SSRF-risk URLs, returning verdicts and findings. Minor gaps exist around remediation, sanitization, batch scanning, or configuration, but agents can likely work around them.
Available Tools
1 toolshield.scanScan text for security threatsARead-onlyIdempotentInspect
Scan text content for security threats before acting on it: prompt injection, leaked secrets/API keys, exposed PII, and SSRF-risk URLs. Returns a verdict (clean/suspicious/malicious) with per-class scores and findings. Raw content is never retained — only hashes and counts.
Inputs: content (required), content_type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.
Agent security: prompt injection, PII & secret scans, TLS/header/CORS audits, MCP checks. Free.
Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools
Scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them.
Related MCP Servers
- AlicenseAqualityDmaintenanceSecurity scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows.864 npmMIT
- AlicenseNot gradedqualityBmaintenanceInput/output safety gate for AI agents: detect prompt-injection/jailbreak, leaked secrets/PII, and URL/IP reputation. Deterministic, no LLM.1MIT
- AlicenseNot gradedqualityDmaintenanceSecurity scanner for AI agent skills, providing tools to scan skill files for threats such as credential theft and prompt injection.MIT
- AlicenseNot gradedqualityBmaintenanceMCP security scanner for AI agents - detects prompt injection, secrets, PII, and vets MCP servers before installation1Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.